def test_cds_removal(self):
record = Record(Seq("A" * 1000))
cluster = helpers.DummyCluster(0, 1000)
record.add_cluster(cluster)
first_cds = helpers.DummyCDS(0, 100, locus_tag="A")
second_cds = helpers.DummyCDS(200, 300, locus_tag="B")
record.add_cds_feature(first_cds)
record.add_cds_feature(second_cds)
assert len(record.get_cds_features()) == 2
assert len(cluster.cds_children) == 2
record.remove_cds_feature(first_cds)
assert len(record.get_cds_features()) == 1
assert len(cluster.cds_children) == 1
assert record.get_cds_features()[0] is list(cluster.cds_children)[0]
assert record.get_cds_features()[0].locus_tag == "B"
def setUp(self):
# locations: VVV VVV
record = Record(Seq("ATGTTATGAGGGTCATAACAT", generic_dna))
record.add_cds_feature(DummyCDS(0, 9, strand=1))
record.add_cds_feature(DummyCDS(12, 21, strand=-1))
cluster_loc = FeatureLocation(0, 21)
cluster = Cluster(cluster_loc, 0, 0, [])
record.add_cluster(cluster)
# if these aren't correct, the tests will fail
assert len(cluster.cds_children) == 2
for cds in record.get_cds_features():
assert cds.overlaps_with(cluster)
assert cds.cluster == cluster, str(cds.location)
assert cds.extract(record.seq) == "ATGTTATGA", str(cds.location)
self.record = record
def setUp(self):
# locations: VVV VVV
record = Record(Seq("ATGTTATGAGGGTCATAACAT"))
record.add_cds_feature(DummyCDS(0, 9, strand=1))
record.add_cds_feature(DummyCDS(12, 21, strand=-1))
cluster = DummyProtocluster(start=0, end=21)
record.add_protocluster(cluster)
record.create_candidate_clusters()
record.create_regions()
# if these aren't correct, the tests will fail
assert len(cluster.cds_children) == 2
assert len(record.get_regions()) == 1
for cds in record.get_cds_features():
assert cds.is_contained_by(cluster)
assert cds.extract(record.seq) == "ATGTTATGA", str(cds.location)
self.record = record
def get_anchor_gene_names(record: Record) -> List[str]:
""" Finds all gene names that have a CDS with secondary metabolite
annotations.
Requires that a CDS.get_name() returns the same name of its parent
Gene.get_name()
Arguments:
record: the record to search
Returns:
a list of gene names
"""
anchor_genes = []
for feature in record.get_cds_features():
if feature.gene_function == GeneFunction.CORE:
anchor_genes.append(feature.get_name())
return anchor_genes
class TestCluster(unittest.TestCase):
def create_cluster(self, start, end):
return Cluster(FeatureLocation(start, end, strand=1),
cutoff=1, extent=1, products=['a'])
def create_cds(self, start, end, strand=1):
return CDSFeature(FeatureLocation(start, end, strand),
locus_tag="%d-%d" % (start, end))
def setUp(self):
self.record = Record(Seq("A" * 1000))
self.start = 100
self.end = 900
self.cluster = self.create_cluster(self.start, self.end)
self.record.add_cluster(self.cluster)
assert self.cluster.location.start == self.start
assert self.cluster.location.end == self.end
def test_trim_unattached(self):
cluster = self.create_cluster(1, 2)
cluster.trim_overlapping()
assert self.cluster.location.start == self.start
assert self.cluster.location.end == self.end
def test_trim_empty(self):
self.cluster.trim_overlapping()
assert self.cluster.location.start == self.start
assert self.cluster.location.end == self.end
def test_trim_contained(self):
starts = [200, 300, 500]
ends = [250, 350, 600]
for start, end in zip(starts, ends):
feature = self.create_cds(start, end)
self.record.add_cds_feature(feature)
assert feature.cluster == self.cluster
self.cluster.trim_overlapping()
assert self.cluster.location.start == self.start
assert self.cluster.location.end == self.end
for cds in self.record.get_cds_features():
self.record.remove_cds_feature(cds)
assert not self.cluster.cds_children
for start, end in zip(starts, ends):
feature = self.create_cds(start, end, strand=-1)
self.record.add_cds_feature(feature)
assert feature.cluster == self.cluster
self.cluster.trim_overlapping()
assert self.cluster.location.start == self.start
assert self.cluster.location.end == self.end
def test_trim_leading_overlap(self):
self.record.add_cds_feature(self.create_cds(self.start - 3, self.start + 3))
self.record.add_cds_feature(self.create_cds(self.start + 20, self.end - 20))
self.cluster.trim_overlapping()
assert self.cluster.location.start == self.start + 3
assert self.cluster.location.end == self.end
def test_trim_leading_overlap_with_overlapping_contained(self): # pylint: disable=invalid-name
self.record.add_cds_feature(self.create_cds(self.start - 3, self.start + 3))
self.record.add_cds_feature(self.create_cds(self.start + 1, self.start + 10))
self.cluster.trim_overlapping()
assert self.cluster.location.start == self.start + 1
assert self.cluster.location.end == self.end
def test_trim_trailing_overlap(self):
self.record.add_cds_feature(self.create_cds(self.end - 3, self.end + 3))
self.record.add_cds_feature(self.create_cds(self.start + 20, self.end - 20))
self.cluster.trim_overlapping()
assert self.cluster.location.start == self.start
assert self.cluster.location.end == self.end - 3
def test_trim_trailing_overlap_with_overlapping_contained(self): # pylint: disable=invalid-name
self.record.add_cds_feature(self.create_cds(self.end - 3, self.end + 3))
self.record.add_cds_feature(self.create_cds(self.end - 10, self.end - 1))
self.cluster.trim_overlapping()
assert self.cluster.location.start == self.start
assert self.cluster.location.end == self.end - 1
def test_products(self):
assert self.cluster.products == ("a",)
self.cluster.add_product("b")
assert self.cluster.products == ("a", "b")
with self.assertRaises(AttributeError):
self.cluster.products.append("c") # pylint: disable=no-member
with self.assertRaises(AssertionError):
self.cluster.add_product(None)
with self.assertRaises(AssertionError):
self.cluster.add_product(["C"])
